© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55853
    Prev
    Next
    INDEX
    Explanations

    ask for, scalp hair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ĵçİ°åľ¨
    -0.10
    ä¾Ŀ
    -0.09
    è²Įä¼¼
    -0.09
    èĮļ
    -0.09
     compens
    -0.08
    éĩįéĩį
    -0.08
    èı½
    -0.08
    åĥ§
    -0.08
    ä»¿ä½Ľ
    -0.08
    æĬķèµĦ人
    -0.08
    POSITIVE LOGITS
    åĬĿ
    0.09
    丼
    0.09
    è·µ
    0.09
    ç»Ŀ大éĥ¨åĪĨ
    0.08
    æįİ
    0.08
     ÑģÑĤан
    0.08
    -expand
    0.08
     Serg
    0.08
    ser
    0.08
     majority
    0.08
    Activations Density 0.002%

    No Known Activations